Non-intrusive load monitoring can obtain classified load data in a user acceptable way, which is of great significance for the user’s energy use behavior and demand response behavior guidance. Taking into account the increase in the type and number of loads, the cost control of embedded device calculation and storage, as well as the cost control of data acquisition equipment. It is becoming more and more important to construct representative data organization patterns and design accurate and efficient load decomposition algorithms for NILM technology. Since traditional non-intrusive load identification generally relies on fine-grained electricity consumption data (second-level resolution, millisecond level resolution), hardware investment and communication overhead are increased. This paper presents a coarse-grained electricity consumption data decomposition algorithm based on the YOLO object detection model. The algorithm adaptively extracts and reassembles minute level power sequences and labels them automatically. This form of data organization will greatly reduce the footprint of storage space, while reducing hardware investment and even relying on the minute level coarse-grained electricity consumption data of existing energy meters. Through the joint design and optimization of the target detection model, the problem of load identification and classification is transformed into a regression problem, which makes the algorithm have high scalability and portability. Through the validation of NILM public data set, it is proved that this method has good non-intrusive load monitoring performance, improves the processing speed and precision of balance, and has high robustness.

Electric vehicles have the advantages of zero emissions and high energy efficiency. They have a broad potential in today’s social life, especially in China where they have been widely used. In the current situation, whereby the storage capacity of electric vehicles is continually increasing and the requirements for grid stability are getting higher and higher, V2G technology emerges to keep up with the times. Since the electric vehicle charging station is a large-scale electric vehicle cluster charging terminal, it is necessary to pay attention to the status and controllability of each charging pile. In view of the lack of attention to the actual operation of the electric vehicle charging station in the existing vehicle–network interaction mode, the charging state of the current electric vehicle charging station is fixed. In this paper, deep learning is used to establish a load perception model for electric vehicle charging stations, and K-means clustering is used to optimize the load perception model to realize random load perception and non-intrusive load monitoring stations for electric vehicle charging. The calculation example results show that the proposed method has good performance in the load perception and controllability evaluation of electric vehicle charging stations, and it provides a feasible solution for the practical realization of electric vehicle auxiliary response.

In recent years, with the rapid development of electric vehicles (EVs), the connection of a large number of EVs to the power grid has adversely affected the economic operation and system stability of the power grid. Therefore, research on the effective dispatch of EVs is of great significance. This paper proposes a day-ahead scheduling strategy for EVs based on converted economical objective, which makes full use of the flexibility of EV loads, takes into account the interests of the grid side and the user side, and reduces the negative impact of EVs connected to the grid. For the limitation of the objective function with the smallest variance, objective function converts the technical index of grid load peak-to-valley difference into an economic index with the smallest charging cost for users, and uses CPLEX to solve the day-ahead scheduling model of small-scale fast charging stations. The calculation example shows that this strategy can effectively reduce the peak-to-valley difference of grid load, which proves the rationality of the strategy.

The current rapid development and large number of applications of electric vehicles make it necessary to further strengthen the research on the state sensing and demand responsiveness of electric vehicles for residential measurements. Based on the non-intrusive load monitoring technology and deep learning algorithm, the user’s power data is processed to obtain the start and end time of possible EV charging behavior, and then the user’s power magnitude data and the obtained possible charging start and end time data are used as the input data of BP neural network to identify the EV charging behavior and establish the load sensing model of residential EVs. Based on the load perception model of electric vehicles, we identify the electric load data of residential measurement, obtain the charging status information such as power and electricity of electric vehicles of users, and use the status information as the data base to evaluate the demand response capability of residential measurement electric vehicles. Finally, the simulation modeling of the above method shows that the method can identify the charging status of electric vehicles more accurately and effectively evaluate the ability of residential measurement electric vehicles to participate in demand response.

Electric vehicles have the advantages of zero carbon emission, high energy efficiency and simple structure, and have been widely used today. Under the control of V2G, electric vehicles can be used as loads and distributed power sources, and become participants in the operation of auxiliary systems. Aiming at how to evaluate the load states and controllability of electric vehicle charging stations, this paper proposes a load sensing method for electric vehicle charging stations based on unsupervised learning and non-intrusive load monitoring. The proposed load sensing method firstly establishes the load sensing model according to the unsupervised learning strategy, and then uses the neural network model of the supervised learning strategy to evaluate the available regulation capability, so as to realize the load perception and regulation capability evaluation of the electric vehicle charging station. Through the verification of simulation data, it is proved that the proposed method has good performance in the evaluation of load perception and controllability of electric vehicle charging stations, which provides a feasible solution to the practical implementation of auxiliary responses by electric vehicles.

Non-intrusive load monitoring has broad application prospects because of its low implementation cost and little interference to energy users, which has been highly expected in the industrial field recently due to the development of learning algorithms. Targeting at the investigation of practical and reliable load monitoring in field implementations, a non-intrusive load disaggregation approach based on an enhanced neural network learning algorithm is proposed in this article. The presented appliance monitoring approach establishes the neural network model following the supervised learning strategy at first and then utilizes the unsupervised learning based optimization to enhance the flexibility and adaptability for diverse scenarios, leading to the improvement of disaggregation performance. By verifications on the REDD public dataset, the proposed approach is demonstrated to be with good performance in non-intrusive load monitoring. In addition to the accuracy enhancement, the proposed approach is also with good scalability, which is efficient in recognizing the newly added appliance.</p>